Skip to content

Pull requests: vllm-project/vllm

New pull request New
475 Open 5,524 Closed
475 Open 5,524 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Properly check if all fused layers are in the list of targets ready ONLY add when PR is ready to merge/full CI is needed
#12666 opened Feb 2, 2025 by eldarkurtic Loading…
1
Fix broken cmake on AMD platform ci/build
#12665 opened Feb 2, 2025 by kagurazakasanae Loading…
1
[AMD][ROCm] Enable DeepSeek model on ROCm
#12662 opened Feb 2, 2025 by hongxiayang Loading…
1
[VLM] Implement merged multimodal processor and V1 support for idefics3
#12660 opened Feb 2, 2025 by Isotr0py • Draft
2 of 4 tasks
@DarkLight1337
1
[Bugfix] Update Prometheus datasource configuration to use variable UID
#12659 opened Feb 2, 2025 by liuyanyi Loading…
2
[WIP] Hybrid allocator for full attention & sliding window attention interleaved models needs-rebase v1
#12655 opened Feb 2, 2025 by heheda12345 • Draft
2
[WIP][Attention] KV Splits heuristic for MLA
#12654 opened Feb 2, 2025 by LucasWilkinson • Draft
1
[Frontend] support AWS SageMaker inference id documentation Improvements or additions to documentation frontend
#12652 opened Feb 1, 2025 by bmuskalla Loading…
2
Fix: benchmark_prioritization.py has problems constructing requests w…
#12646 opened Feb 1, 2025 by Accelerator1996 Loading…
1
2
[V1][Metrics] Add several request timing histograms ready ONLY add when PR is ready to merge/full CI is needed v1
#12644 opened Feb 1, 2025 by markmc • Draft
1
[Core] BatchLLM for better shared prefix utilizing in offline scenarios frontend
#12641 opened Feb 1, 2025 by xinji1 Loading…
2
[Hardware][Metal] Apple Metal support ci/build
#12640 opened Feb 1, 2025 by skyzh • Draft
1
1
[WIP][Attention] WIP MLA with chunked prefill
#12639 opened Feb 1, 2025 by LucasWilkinson • Draft
1
Fix get_device_name for cuda platforms that return bytes
#12636 opened Feb 1, 2025 by mgoin Loading…
7
[Model][Quant] Fix GLM, Fix fused module mappings for quantization
#12634 opened Jan 31, 2025 by kylesayrs • Draft
10
[Core] choice-based structured output with xgrammar ci/build ready ONLY add when PR is ready to merge/full CI is needed structured-output
#12632 opened Jan 31, 2025 by russellb Loading…
5
[Build] update requirements of no-device for plugin usage ci/build
#12630 opened Jan 31, 2025 by sducouedic Loading…
1
[Core] Add Additional Metrics to vLLM Server
#12627 opened Jan 31, 2025 by sahelib25 Loading…
1
6
[CI] Fix flaky CI test ci/build speculative-decoding
#12626 opened Jan 31, 2025 by NickLucche Loading…
2
[ROCm] Using a more precise memory profiling
#12624 opened Jan 31, 2025 by gshtras Loading…
1
[Hardware][TPU] Multi-LoRA implementation for the TPU backend
#12623 opened Jan 31, 2025 by Akshat-Tripathi Loading…
8
Default to generation_config from model frontend
#12622 opened Jan 31, 2025 by hmellor Loading…
1
1
[Core] Improve hash collision avoidance in prefix caching needs-rebase ready ONLY add when PR is ready to merge/full CI is needed v1
#12621 opened Jan 31, 2025 by russellb Loading…
5
Adding cpu inference with VXE ISA for s390x architecture ci/build
#12613 opened Jan 31, 2025 by dilipgb Loading…
1
Fix quark fp8 format loading
#12612 opened Jan 31, 2025 by fxmarty-amd Loading…
1
ProTip! What’s not been updated in a month: updated:<2025-01-02.